FreeMotion: A Unified Framework for Number-Free Text-to-Motion Synthesis
Abstract
Text-to-motion synthesis is a crucial task in computer vision. Existing methods are limited in their universality, as they are tailored for single-person or two-person scenarios and can not be applied to generate motions for more individuals. To achieve the number-free motion synthesis, this paper reconsiders motion generation and proposes to unify the single and multi-person motion by the conditional motion distribution. Furthermore, a generation module and an interaction module are designed for our FreeMotion framework to decouple the process of conditional motion generation and finally support the number-free motion synthesis. Besides, based on our framework, the current single-person motion spatial control method could be seamlessly integrated, achieving precise control of multi-person motion. Extensive experiments demonstrate the superior performance of our method and our capability to infer single and multi-human motions simultaneously.
Cite
Text
Fan et al. "FreeMotion: A Unified Framework for Number-Free Text-to-Motion Synthesis." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-73242-3_6Markdown
[Fan et al. "FreeMotion: A Unified Framework for Number-Free Text-to-Motion Synthesis." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/fan2024eccv-freemotion/) doi:10.1007/978-3-031-73242-3_6BibTeX
@inproceedings{fan2024eccv-freemotion,
title = {{FreeMotion: A Unified Framework for Number-Free Text-to-Motion Synthesis}},
author = {Fan, Ke and Tang, Junshu and Cao, Weijian and Yi, Ran and Li, Moran and Gong, Jingyu and Zhang, Jiangning and Wang, Yabiao and Wang, Chengjie and Ma, Lizhuang},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-73242-3_6},
url = {https://mlanthology.org/eccv/2024/fan2024eccv-freemotion/}
}